Using text mining and machine learning for detection of child abuse

Chintan Amrit Amrit, Tim Paauw, Robin Aly, Miha Lavric, Miha Lavric

Research output: Contribution to journalArticleAcademicpeer-review

34 Downloads (Pure)

Abstract

Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.
Original languageEnglish
Pages (from-to)-
Number of pages39
JournalArxiv.org
Publication statusPublished - 16 Nov 2016

Fingerprint

Learning systems
Health
Public health
Decision support systems
Application programming interfaces (API)

Keywords

  • METIS-318967
  • IR-102420

Cite this

Amrit, C. A., Paauw, T., Aly, R., Lavric, M., & Lavric, M. (2016). Using text mining and machine learning for detection of child abuse. Arxiv.org, -.
Amrit, Chintan Amrit ; Paauw, Tim ; Aly, Robin ; Lavric, Miha ; Lavric, Miha. / Using text mining and machine learning for detection of child abuse. In: Arxiv.org. 2016 ; pp. -.
@article{7c5d9f4ed806438fa8eaf6789a93011c,
title = "Using text mining and machine learning for detection of child abuse",
abstract = "Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.",
keywords = "METIS-318967, IR-102420",
author = "Amrit, {Chintan Amrit} and Tim Paauw and Robin Aly and Miha Lavric and Miha Lavric",
note = "ArXiv preprint arXiv: 1611.03660",
year = "2016",
month = "11",
day = "16",
language = "English",
pages = "--",
journal = "Arxiv.org",
publisher = "Cornell University",

}

Amrit, CA, Paauw, T, Aly, R, Lavric, M & Lavric, M 2016, 'Using text mining and machine learning for detection of child abuse' Arxiv.org, pp. -.

Using text mining and machine learning for detection of child abuse. / Amrit, Chintan Amrit; Paauw, Tim; Aly, Robin; Lavric, Miha; Lavric, Miha.

In: Arxiv.org, 16.11.2016, p. -.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Using text mining and machine learning for detection of child abuse

AU - Amrit, Chintan Amrit

AU - Paauw, Tim

AU - Aly, Robin

AU - Lavric, Miha

AU - Lavric, Miha

N1 - ArXiv preprint arXiv: 1611.03660

PY - 2016/11/16

Y1 - 2016/11/16

N2 - Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.

AB - Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.

KW - METIS-318967

KW - IR-102420

M3 - Article

SP - -

JO - Arxiv.org

JF - Arxiv.org

ER -

Amrit CA, Paauw T, Aly R, Lavric M, Lavric M. Using text mining and machine learning for detection of child abuse. Arxiv.org. 2016 Nov 16;-.